Arao AI
Back to search results

Qwen3-4B-Thinking-2507 · Q5_K_S

Start a discussion
AMD Radeon RX 9070 GRE12GBllama.cpp v0.49L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-4B-Thinking-2507 (Q5_K_S) on AMD Radeon RX 9070 GRE with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

85.62 tok/s

Decode

Decode speed

376.76 tok/s

Prefill

Prefill speed

1.37 s

TTFT

Time to first token

9.66 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

5 days ago

Last verified

Performance

  1. llama.cpp · Q3_K_M Decode 100.99 · Prefill 537.73 ·
  2. llama.cpp · Q5_K_S (current)Decode 85.62 · Prefill 376.76 ·

Core figures

Decode (avg)
85.62 tok/s
Prefill (avg)
376.76 tok/s
TTFT (avg)
1.37 s
VRAM (avg)
9.66 GB
MTP acceptance rate
—
TTFB
0.68 GB
Power draw
228.7 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-4B-Thinking-2507
Quantization
Q5_K_S
Framework
llama.cpp
Version
v0.49
Context length
4096 tokens
Batch size
512
GPU layers
28
Flash Attention
On

Hardware

Nominal and measured figures are shown side by side; whether it runs is the reader's call

GPU
AMD Radeon RX 9070 GRE
Nominal VRAM
12 GB
Measured VRAM (avg)
9.66 GB
OS
Ubuntu 24.04
Driver
amdgpu 6.11
CUDA
N/A
Power draw
228.7 W

Sources & evidence

1 measured records in total, each traceable to its original source

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-13

    v0.49 · Ubuntu 24.04 · CUDA N/A · 4096 ctx

    85.62 tok/s

    Decode

    376.76 tok/s

    Prefill

    1.37 s

    TTFT

    9.66 GB

    VRAM

    —

    MTP

    228.7 W

    Power draw

    L2 batch seed 2026-10-13: llama.cpp on hw_id=32 running model_id=57 at Q5_K_S